knowledge_sememolution_skill

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/npc-worldwide-knowledge-sememolution-skill

About

Use cases: ml, productivity, knowledge-base, deep-research

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools

No tools found

Secrets

None asked for

Install scripts

None found

Runs as

Python package

What's inside

Skill name

knowledge_sememolution_skill

Description

Skill for population-based Knowledge Graph evolution via Sememolution. Use this when the user wants creative cross-domain synthesis, speculative reasoning, or when a single KG search might be too narrow. Sememolution maintains a population of KG "individuals". Each individual has its own graph (different facts, concepts, links) and its own genome controlling how it searches and evolves. Core genome parameters: - `lambda_depth` — Poisson rate for search traversal depth - `lambda_breadth` — Poisson rate for search breadth per step - `sleep_ops` — which refinement ops to apply during sleep - `dream_probability` — chance of speculative synthesis per cycle Workflow: 1. Create a population: `SememolutionPopulation(model, provider, population_size=100, sample_size=10)` 2. Initialize: `pop.initialize()` 3. Assimilate text: `pop.assimilate_text(chunk)` — each individual absorbs it differently 4. Sleep cycle: `pop.sleep_cycle()` — each individual prunes/deepens independently 5. Query and rank: `pop.query_and_rank(question)` — sample individuals, each searches its own graph with Poisson-sampled depth/breadth, generates a response, and responses are ranked. Winners get fitness bumps. 6. Evolve: `pop.evolve_generation()` — tournament selection, crossover, mutation. When to use this: - The user asks open-ended "what if" or "how might X relate to Y" questions - You need diverse perspectives on the same knowledge corpus - You want to discover non-obvious connections across domains - Standard KG search returns shallow or overly literal results Important: this is computationally expensive. Only invoke after checking whether standard keyword/embedding/hybrid search is sufficient.

License

MIT

Instructions

32 lines in SKILL.md · view on GitHub

# knowledge_sememolution_skill

Skill for population-based Knowledge Graph evolution via Sememolution. Use this when the user wants creative cross-domain synthesis, speculative reasoning, or when a single KG search might be too narrow.
Sememolution maintains a population of KG "individuals". Each individual has its own graph (different facts, concepts, links) and its own genome controlling how it searches and evolves.
Core genome parameters: - `lambda_depth` — Poisson rate for search traversal depth - `lambda_breadth` — Poisson rate for search breadth per step - `sleep_ops` — which refinement ops to apply during sleep - `dream_probability` — chance of speculative synthesis per cycle
Workflow: 1. Create a population: `SememolutionPopulation(model, provider, population_size=100, sample_size=10)` 2. Initialize: `pop.initialize()` 3. Assimilate text: `pop.assimilate_text(chunk)` — each individual absorbs it differently 4. Sleep cycle: `pop.sleep_cycle()` — each individual prunes/deepens independently 5. Query and rank: `pop.query_and_rank(question)` — sample individuals, each searches
   its own graph with Poisson-sampled depth/breadth, generates a response,
   and responses are ranked. Winners get fitness bumps.
6. Evolve: `pop.evolve_generation()` — tournament selection, crossover, mutation.
When to use this: - The user asks open-ended "what if" or "how might X relate to Y" questions - You need diverse perspectives on the same knowledge corpus - You want to discover non-obvious connections across domains - Standard KG search returns shallow or overly literal results
Important: this is computationally expensive. Only invoke after checking whether standard keyword/embedding/hybrid search is sufficient.

## Inputs

- `name` (default: `'task'`)
- `description` (default: `'initialize | assimilate | query_rank | evolve | sleep'`)
- `name` (default: `'population_size'`)
- `description` (default: `'Number of individuals (default 100)'`)
- `name` (default: `'query_text'`)
- `description` (default: `'Question to ask the population (for query_rank)'`)

## Steps

- `instruct` → [`instruct.py`](./instruct.py)

## Usage

```
/run_jinx jinx_ref=knowledge_sememolution_skill input_values={"name": "query_text", "description": "Question to ask the population (for query_rank)"}
```

Signals

Stars

1,519

Forks

130

Open issues

6

Last commit (this folder)

Jun 20, 2026 (4 months ago)

Last release

Oct 12, 2026 (18 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License

MIT

Repository

github.com/NPC-Worldwide/npcpy

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

GitHubgithub-graphql